AI Potluck
Contribute
Back to Gap Map Model components / Inference code

Cerebras Inference

Cerebras Systems
closed / Overall score: 4.0(strong)

Cerebras Inference runs on the Cerebras Wafer-Scale Engine (WSE-3), a single silicon wafer with 4 trillion transistors and 44GB of on-chip SRAM. It is delivered as a hosted, API-only cloud service that serves a catalog of models through an OpenAI-compatible API. Cerebras Systems builds and operates the underlying hardware and service.

Openness

1 high confidence
1.0
engine
proprietary(WSE wafer-scale stack)
source
closed
access
managed-cloud-API-only
license
Proprietary

Proprietary cloud inference on custom wafer-scale hardware, reachable only through an API. The inference page offers managed API access with no source or weights release, and the Inference Terms and Conditions grant nothing more than a non-exclusive, limited, non-transferable and non-sublicensable right to access the hosted services.

  • https://d7umqicpi7263.cloudfront.net/eula/4rCqa7snChhObjYFAYH325D2kcqkCRpGXBZYsSMc3mg recorded 2026-09-23

    we hereby grant to you or your Named Users a non-exclusive, limited, non-transferable, non-sublicensable right to access and use the Services, solely for your or their internal business purposes

  • https://www.cerebras.ai/inference recorded 2026-09-23

    Cerebras Inference is a hosted cloud service (tiers: Free Trial with "Get API Key", Developer pay-per-token, Enterprise), with "OpenAI API compatibility" advertised as the integration path; a full-text read of the page finds no source repository, no downloadable weights and no self-hostable implementation - the Enterprise tier's "custom model weights" refers to customer-supplied weights served on Cerebras hardware, not a weights release.

Adoption

3 low confidence
3.0

Cerebras discloses no developer or user count for Inference. The page instead carries customer quotes attributed to GSK, Perplexity and AlphaSense, along with one from Andrew Ng of DeepLearning.AI; none gives a usage figure.

  • https://www.cerebras.ai/inference recorded 2026-09-29

    Customer testimonials appear on the page, including "With Cerebras’ inference speed, GSK is developing innovative AI applications", quotes credited to the "CTO and co-founder, Perplexity" and "CTO and co-founder, AlphaSense", and a quote from Andrew Ng, "Founder, DeepLearning.AI"; no aggregate developer or user count found.

Capability

5 high confidence
5.0

Cerebras is the fastest provider on Artificial Analysis's gpt-oss-120b provider leaderboard, at roughly 1,759 output tokens per second, about 2.5 times the next-fastest provider, SambaNova, with Groq third. The ranking covers a single model and comes from Artificial Analysis's measurements rather than on Cerebras's own claims.

Verified 2026-09-23